CN114485947B - Security monitoring method for outdoor electric equipment - Google Patents
Security monitoring method for outdoor electric equipment Download PDFInfo
- Publication number
- CN114485947B CN114485947B CN202111661461.XA CN202111661461A CN114485947B CN 114485947 B CN114485947 B CN 114485947B CN 202111661461 A CN202111661461 A CN 202111661461A CN 114485947 B CN114485947 B CN 114485947B
- Authority
- CN
- China
- Prior art keywords
- electric equipment
- monitoring
- outdoor electric
- temperature
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 130
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000002159 abnormal effect Effects 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 claims description 35
- 238000012216 screening Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 3
- 238000009529 body temperature measurement Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012546 transfer Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/02—Constructional details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Abstract
The invention provides a security monitoring method for outdoor electric equipment, and relates to the technical field of outdoor security. According to the invention, the air inlet position and the air outlet position of the outdoor electric equipment are measured through the visible light images and the infrared thermal images at a plurality of angles to obtain the real-time air inlet temperature and the real-time air outlet temperature, the real-time air inlet temperature and the real-time air outlet temperature are compared with the corresponding standard operation temperature intervals, if the outdoor electric equipment is not in the standard operation temperature intervals, the outdoor electric equipment is marked as abnormal operation, the influence of the load rate and the air inlet temperature on the air outlet temperature is considered, and the abnormal monitoring of the outdoor electric equipment can be effectively carried out.
Description
Technical Field
The invention relates to the technical field of outdoor security protection, in particular to a security protection monitoring method for outdoor electric equipment.
Background
In closed campus environments such as campuses, factories, etc., many consumers often need to be located outdoors to ensure proper operation of the campus. Therefore, monitoring of outdoor electric equipment and timely finding of abnormality are also very important contents in security protection.
At present, a plurality of cameras are also usually arranged in the park to realize a security monitoring system in the park, but the security monitoring system is usually used for monitoring personnel. The existing monitoring method for outdoor electric equipment generally obtains internal temperature information through a sensor in a box, and when abnormality occurs, maintenance personnel confirms through a monitoring video.
However, when the sensing equipment in the box is in a problem, the situation in the box cannot be effectively judged only by means of the monitoring video, so that how to accurately and independently acquire the temperature data of the outdoor electric equipment is a problem to be solved.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects of the prior art, the invention provides a security monitoring method for outdoor electric equipment, which solves the problem that the existing monitoring cannot accurately and independently acquire the temperature data of the outdoor electric equipment.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
a security monitoring method for outdoor electric equipment comprises the following steps:
s1, synchronously acquiring visible light images and infrared thermal images of a monitoring area at a plurality of angles in a monitoring time period K;
s2, registering the visible light image and the infrared thermal image at the same angle to enable the monitoring areas of the visible light image and the infrared thermal image to be consistent;
s3, acquiring position information of outdoor electric equipment in visible light images of all angles, wherein the position information comprises equipment positions, air inlet positions and air outlet positions;
s4, acquiring standard operation temperature intervals corresponding to combinations of different load rates and air inlet temperatures of the outdoor electric equipment;
s5, acquiring real-time air outlet temperature and real-time air inlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K based on the position information of the outdoor electric equipment;
and S6, when the real-time air outlet temperature is not in the standard operation temperature interval corresponding to the combination of the real-time load rate and the real-time air inlet temperature, marking the operation state of the corresponding outdoor electric equipment as abnormal operation.
Further, the obtaining the position information of the outdoor electric equipment in the visible light images of each angle includes:
s31, marking polygonal areas of outdoor electric equipment in visible light images of all angles to obtain equipment positions of the outdoor electric equipment;
s32, carrying out polygonal area marking on the positions of the air outlet and the air inlet of the outdoor electric equipment in the visible light images of all angles to obtain the positions of the air outlet and the positions of the air inlet of the outdoor electric equipment.
Further, the obtaining the standard operation temperature interval corresponding to the combination of the different load rates and the air inlet temperature of the outdoor electric equipment includes:
s41, constructing a history operation database:
s411, acquiring the air inlet temperature of an air inlet of outdoor electric equipment in a monitoring time period K' noteqK;
s412, acquiring the air outlet temperature of an air outlet of the outdoor electric equipment in a monitoring time period K' noteqK;
s413, acquiring the running state of the outdoor electric equipment in the monitoring time period K', wherein the running state comprises a load rate and an abnormal state; the abnormal state includes one of normal operation or abnormal operation,
s414, if the abnormal state is normal operation, generating historical operation data of the outdoor electric equipment based on the operation state, the air inlet temperature and the air outlet temperature of the outdoor electric equipment;
s42, generating standard operation temperature intervals corresponding to different load rates and air inlet temperature combinations based on historical operation data of outdoor electric equipment.
Further, based on the position information of the outdoor electric equipment, the real-time air outlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K is obtained, and the method comprises the following steps:
s51a, respectively screening visible light images comprising an air outlet from the visible light images of a plurality of angles in the monitoring time period K;
s52a, performing moving object shielding detection on the air outlets based on different angles to obtain available time windows of the air outlets in each visible light image;
s53a, mapping the position of the air outlet of the visible light image to an infrared thermal image corresponding to an available time window of the air outlet;
s54a, obtaining the highest temperature of the air outlet position in the infrared thermal image in the available time window of the air outlet, and taking the highest temperature as the real-time air outlet temperature.
Further, when the obtained real-time outlet gas temperature is plural:
the area of the polygonal area of the air outlet position corresponding to each real-time air outlet temperature is obtained,
and reserving the real-time air outlet temperature corresponding to the air outlet position with the largest area.
Further, based on the position information of the outdoor electric equipment, acquiring the real-time air inlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K, including:
s51b, respectively screening visible light images comprising an air inlet from the visible light images of a plurality of angles in the monitoring time period K;
s52b, performing moving object shielding detection on the air inlets based on different angles to obtain available time windows of the air inlets in all visible light images;
s53b, mapping the equipment position and the air inlet position of the visible light image to an infrared thermal image corresponding to an available time window of the air inlet;
s54b, rasterizing the infrared thermal image in S53b, wherein the size of the grid is a rectangular size of the minimum detectable size of the acquisition equipment for the minimum external infrared thermal image;
s55b, acquiring the temperature of the target grid as the real-time air inlet temperature; the target grid satisfies a grid that is closest to the air inlet, does not fall within any equipment location, and is not occluded within the available time window of the air inlet.
Further, when the obtained real-time intake air temperature is plural:
obtaining the distance between a target grid corresponding to each real-time air inlet temperature and an air inlet;
and reserving the real-time air inlet temperature corresponding to the position of the air inlet with the minimum distance.
Further, the moving object shielding detection includes:
q1, identifying a moving object i in a monitoring image in a monitoring time period k-1; identifying an object j to be detected in a monitoring image in a monitoring time period k, wherein an overlapping time window T exists between the monitoring time period k and a monitoring time period k-1; the identified object j to be detected is an air inlet or an air outlet;
q2, based on the identified moving object i, acquiring the distance d (i, j) between the moving object i and the object j to be detected in any frame image in the monitoring time period k,
if the distance d (i, j) is smaller than the shielding judgment distance alpha, generating a start tag S (i, j);
if there is a start tag S (i, j) and the distance d (i, j) is greater than the occlusion decision distance alpha, a stop tag E (i, j) is generated,
storing the start tag S (i, j) and the end tag E (i, j) into a tag library C corresponding to the monitoring time period k k ；
Wherein S (i, j) = (t) start ,Mo i ,Ep j )，E(i,j)＝(t end ,Mo i ,Ep j ) Wherein t is start Indicating the shielding start time, t end Mo represents the shielding termination time i Representing the ith moving object information, ep j Representing the j-th object information to be detected;
q3, screening Label library C k If there is a set of start labels S (i, j) and corresponding end labels E (i, j), generating a time window r (i, j) = (t) for shielding the object j to be detected from the moving object i start ,t end )；
Q4, sequencing the shielding time windows R (i, j) in time sequence to obtain a shielding time window set R (i, j) = { R (i, j) of the object j to be detected relative to the moving object i in the monitoring time period k 1 ,...,r(i,j) n ...,r(i,j) N -wherein r (i, j) n Representing an nth occlusion time window in the occlusion time window set;
sequentially acquiring two adjacent shielding time windows R (i, j) in a shielding time window set R (i, j) n And r (i, j) n+1 As the available time window ta (i, j) of the object j to be detected relative to the moving object i,
and only reserving the available time window Ta (i, j) of the object j to be detected relative to the moving object i, which is longer than the shortest temperature detection duration beta, so as to obtain an available time window set Ta (i, j) of the object j to be detected relative to the moving object i.
Further, when there are a plurality of moving objects i, the moving object occlusion detection further includes:
q5, acquiring a shielding time window set R' (i, j) corresponding to all the moving objects i;
sequencing the shielding time windows R' (i, j) in the time axis direction to obtain a shielding time window set R (j) = { R (j) of the object j to be detected relative to all moving objects in the monitoring time period k 1 ,...,r(j) n ...,r(j) N }；
Sequentially acquiring two adjacent shielding time windows r (j) n And r (j) n+1 As an available time window ta (j) of the object j to be detected with respect to all moving objects;
and only reserving the available time windows Ta (j) of the object j to be detected, which is larger than the shortest temperature detection duration beta, relative to all moving objects, so as to obtain an available time window set Ta (j) of the object j to be detected.
Further, the identifying the moving object i in the monitored image in the monitoring period k-1 includes:
based on a moving object recognition algorithm, recognizing the moving object of the monitoring image in the monitoring time period k-1 to obtain a recognition frame sq of the moving object i i ；
Identifying an object j to be detected in the monitoring image in the monitoring time period k to obtain an identification frame sq of the object j to be detected j ；
Acquisition of sq i And sq j If the ratio is smaller than the duty ratio threshold gamma, the moving object i does not execute Q2-Q4 when the occlusion detection of the object j to be detected is performed.
(III) beneficial effects
The invention provides a security monitoring method for outdoor electric equipment. Compared with the prior art, the method has the following beneficial effects:
according to the invention, the air inlet position and the air outlet position of the outdoor electric equipment are measured through the visible light images and the infrared thermal images at a plurality of angles to obtain the real-time air inlet temperature and the real-time air outlet temperature, the real-time air inlet temperature and the real-time air outlet temperature are compared with the corresponding standard operation temperature intervals, if the outdoor electric equipment is not in the standard operation temperature intervals, the outdoor electric equipment is marked as abnormal operation, the influence of the load rate and the air inlet temperature on the air outlet temperature is considered, and the abnormal monitoring of the outdoor electric equipment can be effectively carried out.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a flowchart of a method for detecting shielding of an air outlet, an air inlet or a grid according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the identification monitoring time period for the occlusion detection method of the air outlet, air inlet or grid;
fig. 4 is a schematic diagram of the distance between a moving object and an object to be detected in a shielding detection method for an air outlet, an air inlet or a grid.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the application solves the problem that the existing monitoring cannot accurately and independently acquire the temperature data of the outdoor electric equipment by providing the security monitoring method for the outdoor electric equipment.
The technical scheme in the embodiment of the application aims to solve the technical problems, and the overall thought is as follows:
the temperature of the air inlet position and the air outlet position of the outdoor electric equipment is measured through visible light images and infrared thermal images of a plurality of angles to obtain real-time air inlet temperature and real-time air outlet temperature, the real-time air inlet temperature and the real-time air outlet temperature are compared with corresponding standard operation temperature intervals, if the real-time air inlet temperature and the real-time air outlet temperature are not in the standard operation temperature intervals, the outdoor electric equipment is marked as abnormal in operation, the influence of load rate and air inlet temperature on the air outlet temperature is considered, and the outdoor electric equipment can be effectively monitored abnormally.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments.
Example 1:
as shown in fig. 1, the present invention provides a security monitoring method for outdoor electric equipment, including:
s1, synchronously acquiring visible light images and infrared thermal images of a monitoring area at a plurality of angles in a monitoring time period K;
s2, registering the visible light image and the infrared thermal image at the same angle to enable the monitoring areas of the visible light image and the infrared thermal image to be consistent;
s3, acquiring position information of outdoor electric equipment in visible light images of all angles, wherein the position information comprises equipment positions, air inlet positions and air outlet positions;
s4, acquiring standard operation temperature intervals corresponding to combinations of different load rates and air inlet temperatures of the outdoor electric equipment;
s5, acquiring real-time air outlet temperature and real-time air inlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K based on the position information of the outdoor electric equipment;
and S6, when the real-time air outlet temperature is not in the standard operation temperature interval corresponding to the combination of the real-time load rate and the real-time air inlet temperature, marking the operation state of the corresponding outdoor electric equipment as abnormal operation.
The beneficial effects of this embodiment are:
according to the embodiment of the invention, the air inlet position and the air outlet position of the outdoor electric equipment are measured through the visible light images and the infrared thermal images at a plurality of angles to obtain the real-time air inlet temperature and the real-time air outlet temperature, the real-time air inlet temperature and the real-time air outlet temperature are compared with the corresponding standard operation temperature intervals, if the outdoor electric equipment is not in the standard operation temperature intervals, the outdoor electric equipment is marked as abnormal in operation, the influence of the load rate and the air inlet temperature on the air outlet temperature is considered, and the outdoor electric equipment can be effectively monitored abnormally.
The implementation process of the embodiment of the present invention is described in detail below:
s1, synchronously acquiring visible light images and infrared thermal images of a monitoring area at a plurality of angles in a monitoring time period K.
The monitoring area can be provided with a plurality of image acquisition devices with different positions and angles, and each image acquisition device comprises a visible light image acquisition module and an infrared thermal image acquisition module which are respectively used for acquiring visible light images and infrared thermal images. The number of the specific image acquisition devices can be selected according to the actual needs of the monitoring area, so that the shooting area can cover the monitoring area.
S2, registering the visible light image and the infrared thermal image at the same angle through the existing infrared and visible light image registration algorithm, so that the range of the monitoring areas of the two images is consistent.
S3, acquiring position information of outdoor electric equipment in visible light images of all angles, wherein the method comprises the following steps:
the position information comprises a device position, an air inlet position and an air outlet position, and the device position, the air inlet position and the air outlet position are all polygonal identification frames.
S31, marking polygonal areas of outdoor electric equipment in visible light images of all angles to obtain equipment positions of the outdoor electric equipment; the outdoor electric equipment in the graph can be identified automatically by manual marking or by a trained image identification algorithm based on the neural network;
s32, carrying out polygonal area marking on the positions of the air outlet and the air inlet of the outdoor electric equipment in the visible light images of all angles to obtain the positions of the air outlet and the positions of the air inlet of the outdoor electric equipment. The device is similar to the device in position, and can be marked manually or automatically identify the position of the air outlet and the position of the air inlet in the graph through a trained image identification algorithm based on the neural network.
S4, acquiring standard operation temperature intervals corresponding to combinations of different load rates and air inlet temperatures of outdoor electric equipment, wherein the standard operation temperature intervals comprise:
s41, constructing a history operation database, wherein the construction method comprises S411-S414:
s411, the monitoring time period K 'is the time before the monitoring time period K, and the air inlet temperature of the air inlet of the outdoor electric equipment in the monitoring time period K' noteqK is obtained;
s412, acquiring the air outlet temperature of an air outlet of the outdoor electric equipment in a monitoring time period K' noteqK;
s413, acquiring the running state of the outdoor electric equipment in the monitoring time period K', wherein the running state comprises a load rate and an abnormal state; the abnormal state comprises one of normal operation or abnormal operation, the load rate can be set to a plurality of grades, the more the number of the grades is, the more accurate the data is, but the more the required data amount and the operation amount are increased at the same time, and the load rate can be set according to actual needs.
S414, if the abnormal state is normal operation, generating historical operation data of the outdoor electric equipment based on the operation state, the air inlet temperature and the air outlet temperature of the outdoor electric equipment; through the continuous increase of data, a historical operation database comprising various load rates, air inlet temperature and air outlet temperature combinations can be constructed;
for the intake and exhaust temperatures, the acquired data are data in the normal running state, and the data acquired by the sensors at the air inlet of the equipment can be adopted in S411 and S412, or the intake temperatures acquired by the methods of S51 b-S55 b or S51 a-S54 a can be used.
S42, generating standard operation temperature intervals corresponding to different load rates and air inlet temperature combinations based on historical operation data of outdoor electric equipment. The method can be specifically set as follows:
the historical operation data of the outdoor electric equipment are firstly divided into a plurality of large groups according to different levels of load rates, then the data in each large group are divided into a plurality of small groups according to each level of air inlet temperature, the air inlet temperature classification is similar to the classification of the load rate, the setting can be carried out according to actual needs, for example, each 5 ℃ is a level, and the standard operation temperature of the combination of the load rate and the air inlet temperature is constructed based on the lowest air outlet temperature and the highest air outlet temperature in each small group.
S5, based on the position information of the outdoor electric equipment, acquiring the real-time air outlet temperature and the real-time air inlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K. Specifically comprises two parts S5a and S5 b.
S5a, acquiring the real-time air outlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K based on the position information of the outdoor electric equipment, wherein the specific steps comprise: s51a to S56a,
s51a, respectively screening visible light images comprising an air outlet from the visible light images of a plurality of angles in the monitoring time period K;
s52a, performing moving object shielding detection on the air outlets based on different angles to obtain available time windows of the air outlets in each visible light image; the available time window represents a time period in which the air outlet is not blocked in the monitoring time period K.
S53a, mapping the position of the air outlet of the visible light image to an infrared thermal image corresponding to an available time window of the air outlet;
s54a, obtaining the highest temperature of the air outlet position in the infrared thermal image in the available time window of the air outlet, and taking the highest temperature as the real-time air outlet temperature.
Because a real-time air outlet temperature can be acquired in the images of a plurality of angles, a plurality of real-time air outlet temperatures can be obtained, one of the real-time air outlet temperatures is required to be selected as the final real-time air outlet temperature, and the accuracy of temperature measurement can be influenced by the area of the air outlet in the same image, so that the real-time air outlet temperature corresponding to the image of the air outlet with the largest area is selected, and the method comprises the following steps:
s55a, acquiring the area of a polygonal area of the air outlet position corresponding to each real-time air outlet temperature;
s56a, reserving real-time air outlet temperature corresponding to the air outlet position with the largest area.
At this time, the real-time air outlet temperature of the outdoor electric equipment can be obtained.
S5b, the position information based on the outdoor electric equipment acquires the real-time air inlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K, and the method comprises the following steps: s51b to S55b,
s51b, respectively screening visible light images comprising an air inlet from the visible light images of a plurality of angles in the monitoring time period K;
s52b, performing moving object shielding detection on the air inlets based on different angles to obtain available time windows of the air inlets in all visible light images;
s53b, mapping the equipment position and the air inlet position of the visible light image to an infrared thermal image corresponding to an available time window of the air inlet;
s54b, rasterizing the infrared thermal image in S53b, wherein the size of the grid is a rectangular size of the minimum detectable size of the acquisition equipment for the minimum external infrared thermal image;
and S55b, acquiring the temperature of the target grid as the real-time air inlet temperature.
Similar to the real-time outlet air temperature, there may be a case where a plurality of real-time inlet air temperatures are obtained, from which one is selected as the final real-time inlet air temperature, but unlike the outlet air temperature, the inlet air temperature actually needs to be measured as the temperature near the inlet air, and therefore, the target grid should satisfy the following 3 conditions,
(1) the closest distance to the air inlet in order to obtain the temperature closest to the vicinity of the air inlet;
(2) not belonging to any equipment position, namely a background area, so as to avoid collecting the temperature of the surfaces of other equipment;
(3) and if the intersection exists between the available time window of the grid and the available time window of the air inlet, and the intersection time length meets the shortest temperature detection time length beta of the temperature measuring equipment (namely the response time of the temperature measuring equipment), the selected grid can be used as a target grid.
Similarly, there are cases where a plurality of target grids are obtained from images at a plurality of angles, and in this case, it is necessary to select one of the plurality of target grids, and in consideration of the fact that the closer to the intake port, the more accurate the data is, therefore:
s56b, obtaining the distance between the target grid corresponding to each real-time air inlet temperature and the air inlet;
and S57b, reserving the real-time air inlet temperature corresponding to the target grid with the minimum distance.
For the moving object occlusion detection in S52a, S52b, S55b, the existing image occlusion detection algorithm may be adopted, but considering the actual application scenario of the embodiment of the present invention, another occlusion detection method applicable to the air outlet, the air inlet, or the grid may be provided as follows, as shown in fig. 2, including Q1 to Q5:
q1, in order to shelter from the detection to the object j to be detected in the monitoring image in the monitoring time period k, the monitoring images in the monitoring time periods k and k-1 need to be analyzed, wherein the object to be detected is an air inlet and an air outlet of outdoor electric equipment or a grid in S54b, and the specific steps include:
q11, identifying the moving object i in the monitoring image in the monitoring time period k-1 by utilizing the existing moving object detection algorithm to obtain an identification frame sq of the moving object i i 。
Q12, identifying the object j to be detected in the monitoring image in the monitoring time period k to obtain an identification frame sq of the object j to be detected j . The identification method is not limited, can be selected according to actual needs, and can be marked on the image by utilizing the existing image identification technology or manually in consideration of the relative fixed position of the object to be detected in the picture, so as to obtain the identification frame sq of the object j to be detected j 。
As shown in fig. 3, the monitoring period k and the monitoring period k-1 have an overlapping time window T, and the length of the overlapping time window T should be greater than the minimum requirement of the moving object detection algorithm, for example, the moving object detection algorithm needs at least 10 frames of images to identify the moving object, the length of the monitoring period is fixed to 60s, calculated in 24 frames per second, T can be set to 2s, and the overlapping time window T includes 48 frames of images.
Q13, obtain sq i And sq j If the ratio is smaller than the duty ratio threshold value gamma, for example, gamma=5%, it is considered that the temperature measurement of the subsequent object to be detected is not affected, so that when the occlusion detection of the object j to be detected is performed, the ratio isThe moving object does not perform Q2-Q4. In actual use, the preset duty ratio threshold gamma can be adjusted according to specific conditions, and the condition that some moving objects i are far smaller than the area of the object j to be detected can be removed, so that the acquisition quantity is further reduced.
Q2, based on the identified moving object i, acquiring a distance d (i, j) between the moving object i and an object j to be detected in any frame image in the monitoring time period k, as shown in FIG. 4, including:
q21, identification frame sq of moving object i and object j to be detected for acquiring the frame image i And sq j ；
Q22, acquiring two recognition frames sq i And sq j As the distance d (i, j) of the moving object i from the object j to be detected.
After obtaining the distance d (i, j), judging whether to generate a start tag S (i, j) and a stop tag E (i, j) according to a preset shielding judgment distance alpha, wherein the method specifically comprises the following steps:
q23, judging whether the distance d (i, j) is smaller than the shielding judgment distance alpha, and adjusting the value of the alpha according to actual needs.
If yes, generating a start tag S (i, j), otherwise, not generating the start tag S (i, j).
Judging whether the presence of the start tag S (i, j) is satisfied and the distance d (i, j) is greater than the shielding judgment distance alpha;
if so, a termination tag E (i, j) is generated, otherwise, the termination tag E (i, j) is not generated.
Q24, storing the start tag S (i, j) and the end tag E (i, j) into a tag library C corresponding to the monitoring time period k k ；
Wherein S (i, j) = (t) start ,Mo i ,Ep j )，E(i,j)＝(t end ,Mo i ,Ep j ) Wherein t is start Indicating the shielding start time, t end Mo represents the shielding termination time i Representing the ith moving object information, ep j Representing the j-th object information to be detected.
Q3, based on label library C constructed k The method for acquiring the shielding time window r (i, j) of the object j to be detected relative to the moving object i specifically comprises the following steps:
q31, screening Label library C k If there is a set of start labels S (i, j) and corresponding end labels E (i, j), generating a time window r (i, j) = (t) for shielding the object j to be detected from the moving object i start ,t end )；
To further utilize the tag library C k Can inherit data when acquiring the monitoring period k+1:
q32, if tag library C k If there is a start tag S (i, j) that does not correspond to the end tag E (i, j), then t of the start tag S (i, j) is started before the occlusion time window in the monitoring time period k+1 is acquired start The starting time of the monitoring time period k+1 is replaced, and the starting time is stored in the tag library C corresponding to the monitoring time period k+1 k+1 。
Q33, storing the start tag S (i, j) into the tag library C corresponding to the monitoring time period k+1 k+1 And when the transfer times of the start tag S (i, j) are increased by 1, if the transfer times of the start tag S (i, j) exceed the preset maximum transfer times, deleting the start tag from the tag library, and sending early warning information corresponding to the object to be detected which is blocked for a long time to a maintainer. The maintainer can process the shielding object according to the early warning information.
Q4, analyzing the shielding condition of the object j to be detected relative to the moving object i in the monitoring time period k, and specifically comprising the following steps:
q41, sequencing the shielding time windows R (i, j) in time sequence to obtain a shielding time window set R (i, j) = { R (i, j) of the object j to be detected relative to the moving object i in the monitoring time period k 1 ,...,r(i,j) n ...,r(i,j) N }，
Wherein r (i, j) n And representing an nth occlusion time window in the occlusion time window set, wherein N is the number of elements in the set.
Q42, sequentially acquiring two adjacent shielding time windows R (i, j) in the shielding time window set R (i, j) n And r (i, j) n+1 As the interval of the object j to be detected relative to the moving object i, the usable time window ta (i, j), ta (i, j) indicates that the moving object i is in the ta (i, j) interval, the object j to be detected is not blocked, and the monitoring time periodThere may be a plurality of ta (i, j) within k.
Considering the influence of the performance of the temperature detecting device on the available time window, if the interval time is shorter than the shortest temperature detecting duration beta of the side temperature detecting device, and beta is twice the time required by the temperature detecting device to measure the temperature, the interval time is still unavailable, so that:
q43, only reserving an available time window Ta (i, j) of the object j to be detected, which is larger than the shortest temperature detection duration beta, relative to the moving object i, wherein the available time window Ta (i, j) indicates that in Ta (i, j), enough time is available for temperature measurement, and after traversing all two adjacent shielding time windows in R (i, j), an available time window set Ta (i, j) of the object j to be detected relative to the moving object i is obtained.
Beta depends on the performance of the temperature detection device, and the higher the performance of the temperature detection device is, the shorter the shortest temperature detection duration beta can be set, and the higher the probability of obtaining the available time window ta (i, j) is.
Q5, if a plurality of moving objects exist in the monitoring image, further acquiring possible shielding of all the moving objects to the object j to be detected;
q51, repeating the steps of Q2-Q4 to obtain a shielding time window set R' (i, j) corresponding to all the moving objects i;
q52, sequencing the shielding time windows R' (i, j) in the time axis direction to obtain a shielding time window set R (j) = { R (j) of the object j to be detected relative to all moving objects in the monitoring time period k 1 ,...,r(j) n ...,r(j) N }；
Q53, sequentially acquiring two adjacent shielding time windows r (j) n And r (j) n+1 As an available time window ta (j) of the object j to be detected with respect to all moving objects;
based on the same consideration, it is necessary to determine the influence of the shortest temperature detection period β on the available time window ta (j):
q54, only reserving the available time windows Ta (j) of the object j to be detected, which is larger than the shortest temperature detection duration beta, relative to all moving objects, and traversing all two adjacent shielding time windows in R (j) to obtain an available time window set Ta (j) of the object j to be detected.
In summary, compared with the prior art, the invention has the following beneficial effects:
(1) according to the embodiment of the invention, the air inlet position and the air outlet position of the outdoor electric equipment are measured through the visible light images and the infrared thermal images at a plurality of angles to obtain the real-time air inlet temperature and the real-time air outlet temperature, the real-time air inlet temperature and the real-time air outlet temperature are compared with the corresponding standard operation temperature intervals, if the outdoor electric equipment is not in the standard operation temperature intervals, the outdoor electric equipment is marked as abnormal in operation, the influence of the load rate and the air inlet temperature on the air outlet temperature is considered, and the outdoor electric equipment can be effectively monitored abnormally.
(2) The embodiment of the invention also provides a construction mode of the standard operation temperature interval, a historical operation database is generated by recording the load rate, the air inlet temperature and the air outlet temperature, and the standard operation temperature interval under different load rate and air inlet temperature combinations is calculated based on the data in the historical operation database.
(3) The embodiment of the invention simultaneously provides that when the real-time air outlet temperature and the real-time air inlet temperature are obtained, corresponding algorithms are respectively designed for solving the real-time air outlet temperature and the real-time air inlet temperature according to the outdoor environment and the characteristics of different air outlet temperature and air inlet temperature, the influence of a shielding object on the accuracy of temperature measurement data is considered, the available time windows of the air inlet and the air outlet are calculated, the maximum area is selected as the real-time air outlet temperature, and the optimal target grid temperature is selected as the real-time air inlet temperature.
(4) The embodiment of the invention also provides a shielding detection method for the air outlet, the air inlet or the grid, which is characterized in that a moving object i in a monitoring image in a monitoring time period k-1 is identified, an object j to be detected in the monitoring image in the monitoring time period k is identified, the distance d (i, j) between the moving object i and the object j to be detected is determined in any frame image in the monitoring time period k, and a shielding time window r (i, j) = (t) of the object j to be detected relative to the moving object i is determined based on the distance d (i, j) between the moving object i and the object j to be detected start ,t end ) Further, the available time window ta (i, j) of the object j to be detected relative to the moving object i is obtained, while taking into considerationAnd the influence of the performance of the temperature detection equipment on the available time window is removed, so that the available time window which is insufficient for temperature measurement is removed, and the accuracy of the available time window is obviously improved.
It should be noted that, from the above description of the embodiments, those skilled in the art will clearly understand that each embodiment may be implemented by means of software plus necessary general hardware platform. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the respective embodiments or some parts of the embodiments. In this document, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The security monitoring method for the outdoor electric equipment is characterized by comprising the following steps of:
s1, synchronously acquiring visible light images and infrared thermal images of a monitoring area at a plurality of angles in a monitoring time period K;
s2, registering the visible light image and the infrared thermal image at the same angle to enable the monitoring areas of the visible light image and the infrared thermal image to be consistent;
s3, acquiring position information of outdoor electric equipment in visible light images of all angles, wherein the position information comprises equipment positions, air inlet positions and air outlet positions;
s4, acquiring standard operation temperature intervals corresponding to combinations of different load rates and air inlet temperatures of the outdoor electric equipment;
s5, acquiring real-time air outlet temperature and real-time air inlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K based on the position information of the outdoor electric equipment;
s6, when the real-time air outlet temperature is not in a standard operation temperature interval corresponding to the combination of the real-time load rate and the real-time air inlet temperature, marking the operation state of the corresponding outdoor electric equipment as abnormal operation;
the position information based on the outdoor electric equipment obtains the real-time air outlet temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K, and the position information based on the outdoor electric equipment comprises the following components:
s51a, respectively screening visible light images comprising an air outlet from the visible light images of a plurality of angles in the monitoring time period K;
s52a, performing moving object shielding detection on the air outlets based on different angles to obtain available time windows of the air outlets in each visible light image;
s53a, mapping the position of the air outlet of the visible light image to an infrared thermal image corresponding to an available time window of the air outlet;
s54a, obtaining the highest temperature of the air outlet position in the infrared thermal image in the available time window of the air outlet, and taking the highest temperature as the real-time air outlet temperature;
and the moving object occlusion detection includes:
q1, identifying a moving object i in a monitoring image in a monitoring time period k-1; identifying an object j to be detected in a monitoring image in a monitoring time period k, wherein an overlapping time window T exists between the monitoring time period k and a monitoring time period k-1; the identified object j to be detected is an air inlet or an air outlet;
q2, based on the identified moving object i, acquiring the distance d (i, j) between the moving object i and the object j to be detected in any frame image in the monitoring time period k,
if the distance d (i, j) is smaller than the shielding judgment distance alpha, generating a start tag S (i, j);
if there is a start tag S (i, j) and the distance d (i, j) is greater than the occlusion decision distance alpha, a stop tag E (i, j) is generated,
storing the start tag S (i, j) and the end tag E (i, j) into a tag library C corresponding to the monitoring time period k k ；
Wherein S (i, j) = (t) start ,Mo i ,Ep j )，E(i,j)＝(t end ,Mo i ,Ep j ) Wherein t is start Indicating the shielding start time, t end Mo represents the shielding termination time i Representing the ith moving object information, ep j Representing the j-th object information to be detected;
q3, screening Label library C k If there is a set of start labels S (i, j) and corresponding end labels E (i, j), generating a time window r (i, j) = (t) for shielding the object j to be detected from the moving object i start ,t end )；
Q4, sequencing the shielding time windows R (i, j) in time sequence to obtain a shielding time window set R (i, j) = { R (i, j) of the object j to be detected relative to the moving object i in the monitoring time period k 1 ,...,r(i,j) n ...,r(i,j) N -wherein r (i, j) n Representing an nth occlusion time window in the occlusion time window set;
sequentially acquiring two adjacent shielding time windows R (i, j) in a shielding time window set R (i, j) n And r (i, j) n+1 As the interval of the object j to be detected relative to the moving object iThe time window ta (i, j),
and only reserving the available time window Ta (i, j) of the object j to be detected relative to the moving object i, which is longer than the shortest temperature detection duration beta, so as to obtain an available time window set Ta (i, j) of the object j to be detected relative to the moving object i.
2. The method for security monitoring of outdoor electric equipment according to claim 1, wherein the step of obtaining the position information of the outdoor electric equipment in the visible light images of each angle comprises the steps of:
s31, marking polygonal areas of outdoor electric equipment in visible light images of all angles to obtain equipment positions of the outdoor electric equipment;
s32, carrying out polygonal area marking on the positions of the air outlet and the air inlet of the outdoor electric equipment in the visible light images of all angles to obtain the positions of the air outlet and the positions of the air inlet of the outdoor electric equipment.
3. The method for security monitoring of outdoor electric equipment according to claim 1, wherein the step of obtaining standard operation temperature intervals corresponding to combinations of different load rates and intake air temperatures of the outdoor electric equipment comprises the steps of:
s41, constructing a history operation database:
s411, acquiring the air inlet temperature of an air inlet of outdoor electric equipment in a monitoring time period K' noteqK;
s412, acquiring the air outlet temperature of an air outlet of the outdoor electric equipment in a monitoring time period K' noteqK;
s413, acquiring the running state of the outdoor electric equipment in the monitoring time period K', wherein the running state comprises a load rate and an abnormal state; the abnormal state includes one of normal operation or abnormal operation;
s414, if the abnormal state is normal operation, generating historical operation data of the outdoor electric equipment based on the operation state, the air inlet temperature and the air outlet temperature of the outdoor electric equipment;
s42, generating standard operation temperature intervals corresponding to different load rates and air inlet temperature combinations based on historical operation data of outdoor electric equipment.
4. The method for security monitoring of outdoor electric equipment according to claim 1, wherein when the obtained real-time air outlet temperature is plural:
the area of the polygonal area of the air outlet position corresponding to each real-time air outlet temperature is obtained,
and reserving the real-time air outlet temperature corresponding to the air outlet position with the largest area.
5. The method for security monitoring of outdoor electric equipment according to claim 1, wherein the acquiring the real-time intake temperature of the outdoor electric equipment in the infrared thermal image in the monitoring time period K based on the position information of the outdoor electric equipment comprises:
s51b, respectively screening visible light images comprising an air inlet from the visible light images of a plurality of angles in the monitoring time period K;
s52b, performing moving object shielding detection on the air inlets based on different angles to obtain available time windows of the air inlets in all visible light images;
s53b, mapping the equipment position and the air inlet position of the visible light image to an infrared thermal image corresponding to an available time window of the air inlet;
s54b, rasterizing the infrared thermal image in S53b, wherein the size of the grid is a rectangular size of the minimum detectable size of the acquisition equipment for the minimum external infrared thermal image;
s55b, acquiring the temperature of the target grid as the real-time air inlet temperature; the target grid satisfies a grid that is closest to the air inlet, does not fall within any equipment location, and is not occluded within the available time window of the air inlet.
6. The method for monitoring and controlling outdoor electric equipment according to claim 5, wherein when the obtained real-time intake air temperature is plural:
obtaining the distance between a target grid corresponding to each real-time air inlet temperature and an air inlet;
and reserving the real-time air inlet temperature corresponding to the position of the air inlet with the minimum distance.
7. A monitoring method for maintenance of outdoor objects to be detected according to claim 6, wherein when there are a plurality of moving objects i, the moving object occlusion detection further comprises:
q5, acquiring a shielding time window set R' (i, j) corresponding to all the moving objects i;
sequencing the shielding time windows R' (i, j) in the time axis direction to obtain a shielding time window set R (j) = { R (j) of the object j to be detected relative to all moving objects in the monitoring time period k 1 ,...,r(j) n ...,r(j) N }；
Sequentially acquiring two adjacent shielding time windows r (j) n And r (j) n+1 As an available time window ta (j) of the object j to be detected with respect to all moving objects;
and only reserving the available time windows Ta (j) of the object j to be detected, which is larger than the shortest temperature detection duration beta, relative to all moving objects, so as to obtain an available time window set Ta (j) of the object j to be detected.
8. The monitoring method for outdoor maintenance of objects to be detected according to claim 6, wherein the identifying the moving object i in the monitored image in the monitoring period k-1 comprises:
based on a moving object recognition algorithm, recognizing the moving object of the monitoring image in the monitoring time period k-1 to obtain a recognition frame sq of the moving object i i ；
Identifying an object j to be detected in the monitoring image in the monitoring time period k to obtain an identification frame sq of the object j to be detected j ；
Acquisition of sq i And sq j If the ratio is smaller than the duty ratio threshold gamma, the moving object i does not execute Q2-Q4 when the occlusion detection of the object j to be detected is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111661461.XA CN114485947B (en) | 2021-12-30 | 2021-12-30 | Security monitoring method for outdoor electric equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111661461.XA CN114485947B (en) | 2021-12-30 | 2021-12-30 | Security monitoring method for outdoor electric equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114485947A CN114485947A (en) | 2022-05-13 |
| CN114485947B true CN114485947B (en) | 2024-04-02 |
Family
ID=81497269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111661461.XA Active CN114485947B (en) | 2021-12-30 | 2021-12-30 | Security monitoring method for outdoor electric equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114485947B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115063754B (en) * | 2022-08-18 | 2022-11-01 | 中国工业互联网研究院 | Equipment monitoring method, device, equipment and storage medium based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835032A (en) * | 2010-04-27 | 2010-09-15 | 沈阳瑗玛信息技术有限公司 | Multi-camera crowd-gathered message statistic device and method |
| CN207798262U (en) * | 2017-12-06 | 2018-08-31 | 杭州柯林电气股份有限公司 | Transformer temperature on-line monitoring system based on infrared visible light |
| CN110633682A (en) * | 2019-09-19 | 2019-12-31 | 合肥英睿系统技术有限公司 | Infrared image anomaly monitoring method, device and equipment based on double-light fusion |
| CN110766676A (en) * | 2019-10-24 | 2020-02-07 | 中国科学院长春光学精密机械与物理研究所 | Target detection method based on multi-source sensor fusion |
| CN111861951A (en) * | 2020-06-01 | 2020-10-30 | 浙江双视红外科技股份有限公司 | Infrared light and visible light based dual-waveband monitoring method, device and system |
| CN112734692A (en) * | 2020-12-17 | 2021-04-30 | 安徽继远软件有限公司 | Transformer equipment defect identification method and device |
| CN113487639A (en) * | 2021-07-14 | 2021-10-08 | 北京金山云网络技术有限公司 | Image processing method and device, electronic equipment and storage medium |
-
2021
- 2021-12-30 CN CN202111661461.XA patent/CN114485947B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835032A (en) * | 2010-04-27 | 2010-09-15 | 沈阳瑗玛信息技术有限公司 | Multi-camera crowd-gathered message statistic device and method |
| CN207798262U (en) * | 2017-12-06 | 2018-08-31 | 杭州柯林电气股份有限公司 | Transformer temperature on-line monitoring system based on infrared visible light |
| CN110633682A (en) * | 2019-09-19 | 2019-12-31 | 合肥英睿系统技术有限公司 | Infrared image anomaly monitoring method, device and equipment based on double-light fusion |
| CN110766676A (en) * | 2019-10-24 | 2020-02-07 | 中国科学院长春光学精密机械与物理研究所 | Target detection method based on multi-source sensor fusion |
| CN111861951A (en) * | 2020-06-01 | 2020-10-30 | 浙江双视红外科技股份有限公司 | Infrared light and visible light based dual-waveband monitoring method, device and system |
| CN112734692A (en) * | 2020-12-17 | 2021-04-30 | 安徽继远软件有限公司 | Transformer equipment defect identification method and device |
| CN113487639A (en) * | 2021-07-14 | 2021-10-08 | 北京金山云网络技术有限公司 | Image processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114485947A (en) | 2022-05-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2905665B1 (en) | Information processing apparatus, diagnosis method, and program | |
| US20210183050A1 (en) | Pipe feature identification using pipe inspection data analysis | |
| Adam et al. | Robust real-time unusual event detection using multiple fixed-location monitors | |
| KR20200060372A (en) | Thermography image processing using a neural network to identify the bottom corrosion (CUI) of insulation | |
| JP6774636B2 (en) | Abnormality analysis methods, programs and systems | |
| CN114912852B (en) | Abnormity monitoring and early warning system for storage tank of refrigeration bin | |
| US11580629B2 (en) | System and method for determining situation of facility by imaging sensing data of facility | |
| US20210174086A1 (en) | Ar gauge scanner using a mobile device application | |
| CN114485947B (en) | Security monitoring method for outdoor electric equipment | |
| CN115660262B (en) | Engineering intelligent quality inspection method, system and medium based on database application | |
| CN109313442B (en) | Automated visual and acoustic analysis for event detection | |
| Higa et al. | Robust estimation of product amount on store shelves from a surveillance camera for improving on-shelf availability | |
| CN109001210B (en) | System and method for detecting aging and cracking of sealing rubber strip of civil air defense door | |
| CN108629310B (en) | Engineering management supervision method and device | |
| JP6598962B1 (en) | Fire detection device, fire detection method and fire monitoring system | |
| CN114332587A (en) | Fire disaster identification early warning method and device | |
| EP3712728A1 (en) | Apparatus for predicting equipment damage | |
| CN116524691B (en) | Hidden danger warning method and device for power transmission line, storage medium and computer equipment | |
| CN115965625B (en) | Instrument detection device based on visual recognition and detection method thereof | |
| CN116205885A (en) | Abnormal state detection method, system, electronic device and readable storage medium | |
| CN108760739B (en) | System and method for detecting rust state of civil air defense door | |
| WO2020183781A1 (en) | Abnormality diagnosis device | |
| CN117253176B (en) | Safe production Al intelligent detection method based on video analysis and computer vision | |
| US20240053287A1 (en) | Probability of detection of lifecycle phases of corrosion under insulation using artificial intelligence and temporal thermography | |
| CN117668737B (en) | Pipeline detection data fault early warning checking method and related device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |